keras package - RDocumentation

Learn R Programming

⚠️There's a newer version (2.13.0) of this package.Take me there.

R interface to Keras

Keras is a high-level neural networks API developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Keras has the following key features:

Allows the same code to run on CPU or on GPU, seamlessly.
User-friendly API which makes it easy to quickly prototype deep learning models.
Built-in support for convolutional networks (for computer vision), recurrent networks (for sequence processing), and any combination of both.
Supports arbitrary network architectures: multi-input or multi-output models, layer sharing, model sharing, etc. This means that Keras is appropriate for building essentially any deep learning model, from a memory network to a neural Turing machine.

See the package website at https://rstudio.github.io/keras for complete documentation.

Copy Link

Version

Install

install.packages('keras')

Monthly Downloads

25,525

Version

0.3.14

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/rstudio/keras

Maintainer

JJ Allaire

Last Published

August 15th, 2023

Functions in keras (0.3.14)

Base R6 class for Keras callbacks

Base R6 class for Keras layers

Keras backend tensor engine

Bidirectional wrapper for RNNs.

application_mobilenet

Instantiates the MobileNet architecture.

application_resnet50

ResNet50 model for Keras.

activation_relu

Activation functions

application_inception_v3

Inception V3 model, with weights pre-trained on ImageNet.

application_vgg

VGG16 and VGG19 models for Keras.

application_xception

Xception V1 model for Keras.

callback_model_checkpoint

Save the model after every epoch.

callback_progbar_logger

Callback that prints metrics to stdout.

dataset_boston_housing

Boston housing price regression dataset

callback_tensorboard

TensorBoard basic visualizations

Configure a Keras model for training

Count the total number of scalars composing the weights.

callback_csv_logger

Callback that streams epoch results to a csv file

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

constraint_maxnorm

MaxNorm weight constraint

constraint_minmaxnorm

MinMaxNorm weight constraint

callback_lambda

Create a custom callback

callback_learning_rate_scheduler

Learning rate scheduler.

constraint_nonneg

NonNeg weight constraint

MNIST database of handwritten digits

dataset_reuters

Reuters newswire topics classification

image_data_generator

Generate minibatches of image data with real-time data augmentation.

Loads an image into PIL format.

imagenet_preprocess_input

Preprocesses a tensor encoding a batch of images.

initializer_constant

Initializer that generates tensors initialized to a constant value.

layer_activation

Apply an activation function to an output.

layer_activation_elu

Exponential Linear Unit.

constraint_unitnorm

UnitNorm weight constraint

flow_images_from_data

Generates batches of augmented/normalized data from image data and labels

flow_images_from_directory

Generates batches of data from images in a directory (with optional augmented/normalized data)

Layer/Model configuration

Layer that averages a list of inputs.

layer_average_pooling_1d

Average pooling for temporal data.

layer_cropping_1d

Cropping layer for 1D input (e.g. temporal sequence).

layer_cropping_2d

Cropping layer for 2D input (e.g. picture).

Downloads a file from a URL if it not already in the cache.

initializer_he_normal

He normal initializer.

initializer_he_uniform

He uniform variance scaling initializer.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

layer_embedding

Turns positive integers (indexes) into dense vectors of fixed size.

Flattens an input

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

dataset_cifar10

CIFAR10 small image classification

Train a Keras model

Fits the model on data yielded batch-by-batch by a generator.

Layer/Model weights as R arrays

Representation of HDF5 dataset to be used instead of an R array

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

keras_model_sequential

Keras Model composed of a linear stack of layers

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_average_pooling_3d

Average pooling operation for 3D data (spatial or spatio-temporal).

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

Create a Keras Layer

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

fit_text_tokenizer

Update tokenizer internal vocabulary based on a list of texts or list of sequences.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

Layer that adds a list of inputs.

layer_alpha_dropout

Applies Alpha Dropout to the input.

1D convolution layer (e.g. temporal convolution).

2D convolution layer (e.g. spatial convolution over images).

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

initializer_identity

Initializer that generates the identity matrix.

initializer_lecun_normal

LeCun normal initializer.

initializer_variance_scaling

Initializer capable of adapting its scale to the shape of weights.

Converts a PIL Image instance to a 3d-array.

layer_concatenate

Layer that concatenates a list of inputs.

Layer that computes a dot product between samples in two tensors.

Applies Dropout to the input.

Gated Recurrent Unit - Cho et al.

layer_cropping_3d

Cropping layer for 3D data (e.g. spatial or spatio-temporal).

Add a densely-connected NN layer to an output

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

callback_remote_monitor

Callback used to stream events to a server.

dataset_cifar100

CIFAR100 small image classification

IMDB Movie reviews sentiment classification

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

Reshapes an output to a certain shape.

layer_separable_conv_2d

Depthwise separable 2D convolution.

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_upsampling_2d

Upsampling layer for 2D inputs.

optimizer_adamax

Adamax optimizer

initializer_zeros

Initializer that generates tensors initialized to 0.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_activity_regularization

Layer that applies an update to the cost function based input activity.

layer_conv_3d_transpose

Transposed convolution layer (sometimes called Deconvolution).

Evaluate a Keras model

evaluate_generator

Evaluates the model on a data generator.

Retrieve tensors for layers with multiple nodes

Retrieves a layer based on either its name (unique) or index.

Layer that computes the maximum (element-wise) a list of inputs.

Layer that multiplies (element-wise) a list of inputs.

plot.keras_training_history

Plot training history

Generates probability or class probability predictions for the input samples.

Objects exported from other packages

layer_simple_rnn

Fully-connected RNN where the output is to be fed back to input.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

metric_binary_accuracy

Model performance metrics

Model configuration as JSON

predict_generator

Generates predictions for the input samples from a data generator.

layer_conv_lstm_2d

Convolutional LSTM.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

Permute the dimensions of an input according to a given pattern

layer_repeat_vector

Repeats the input n times.

layer_upsampling_3d

Upsampling layer for 3D inputs.

predict_on_batch

Returns predictions for a single batch of samples.

sequences_to_matrix

Convert a list of sequences into a matrix.

Generates skipgram word pairs.

Single gradient update or model evaluation over one batch of samples.

Long-Short Term Memory unit - Hochreiter 1997.

Masks a sequence by using a mask value to skip timesteps.

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_zero_padding_1d

Zero-padding layer for 1D input (e.g. temporal sequence).

loss_mean_squared_error

Model loss functions

make_sampling_table

Generates a word rank-based probabilistic sampling table.

Stochastic gradient descent optimizer

Pads each sequence to the same length (length of the longest sequence).

texts_to_sequences

Transform each text in texts in a sequence of integers.

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

optimizer_adadelta

Adadelta optimizer.

optimizer_adagrad

Adagrad optimizer.

Remove the last layer in a model

summary.keras.engine.training.Model

Print a summary of a Keras model

text_hashing_trick

Converts a text to a sequence of indexes in a fixed-size hashing space.

Text tokenization utility

texts_to_matrix

Convert a list of texts to a matrix.

predict.keras.engine.training.Model

Generate predictions from a Keras model

save_model_hdf5

Save/Load models using HDF5 files

save_model_weights_hdf5

Save/Load model weights using HDF5 files

time_distributed

Apply a layer to every temporal slice of an input.

Converts a class vector (integers) to binary class matrix.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_conv_2d_transpose

Transposed convolution layer (sometimes called Deconvolution).

3D convolution layer (e.g. spatial convolution over volumes).

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

Wraps arbitrary expression as a layer

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

layer_max_pooling_2d

Max pooling operation for spatial data.

layer_max_pooling_3d

Max pooling operation for 3D data (spatial or spatio-temporal).

layer_zero_padding_2d

Zero-padding layer for 2D input (e.g. picture).

layer_zero_padding_3d

Zero-padding layer for 3D data (spatial or spatio-temporal).

Normalize a matrix or nd-array

optimizer_nadam

Nesterov Adam optimizer

optimizer_rmsprop

RMSProp optimizer

L1 and L2 regularization

Reset the states for a layer

One-hot encode a text into a list of word indexes in a vocabulary of size n.

text_to_word_sequence

Convert text to a sequence of words (or tokens).

Model configuration as YAML

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

mobilenet_decode_predictions

Decodes the prediction of an MobileNet model.